[HTML][HTML] Knowledge graph quality control: A survey
X Wang, L Chen, T Ban, M Usman, Y Guan, S Liu… - Fundamental …, 2021 - Elsevier
A knowledge graph (KG), a special form of semantic network, integrates fragmentary data
into a graph to support knowledge processing and reasoning. KG quality control is important …
into a graph to support knowledge processing and reasoning. KG quality control is important …
Neuro-symbolic artificial intelligence
Abstract Neuro-Symbolic Artificial Intelligence–the combination of symbolic methods with
methods that are based on artificial neural networks–has a long-standing history. In this …
methods that are based on artificial neural networks–has a long-standing history. In this …
EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage …
Abstract The latest Deep Learning (DL) models for detection and classification have
achieved an unprecedented performance over classical machine learning algorithms …
achieved an unprecedented performance over classical machine learning algorithms …
Contextualization and exploration of local feature importance explanations to improve understanding and satisfaction of non-expert users
The increasing usage of complex Machine Learning models for decision-making has raised
interest in explainable artificial intelligence (XAI). In this work, we focus on the effects of …
interest in explainable artificial intelligence (XAI). In this work, we focus on the effects of …
The challenges of integrating explainable artificial intelligence into GeoAI
J Xing, R Sieber - Transactions in GIS, 2023 - Wiley Online Library
Although explainable artificial intelligence (XAI) promises considerable progress in
glassboxing deep learning models, there are challenges in applying XAI to geospatial …
glassboxing deep learning models, there are challenges in applying XAI to geospatial …
Comprehensible artificial intelligence on knowledge graphs: A survey
Artificial Intelligence applications gradually move outside the safe walls of research labs and
invade our daily lives. This is also true for Machine Learning methods on Knowledge …
invade our daily lives. This is also true for Machine Learning methods on Knowledge …
Interpretable classification of Wiki-review streams
Wiki articles are created and maintained by a crowd of editors, producing a continuous
stream of reviews. Reviews can take the form of additions, reverts, or both. This …
stream of reviews. Reviews can take the form of additions, reverts, or both. This …
Designing an Intelligent Contract with Communications and Risk Data
G Stathis, A Trantas, G Biagioni, KA Graaf… - SN Computer …, 2024 - Springer
Contract automation is a challenging topic within Artificial Intelligence and LegalTech. From
digitised contracts via smart contracts, we are heading towards Intelligent Contracts …
digitised contracts via smart contracts, we are heading towards Intelligent Contracts …
Towards human-compatible XAI: Explaining data differentials with concept induction over background knowledge
Abstract Concept induction, which is based on formal logical reasoning over description
logics, has been used in ontology engineering in order to create ontology (TBox) axioms …
logics, has been used in ontology engineering in order to create ontology (TBox) axioms …
Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning
A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons:
accurate interpretations would provide insights into the question of what a deep learning …
accurate interpretations would provide insights into the question of what a deep learning …